[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-reasoning-arena-mistral-cambridge-41pct":3,"topics-all":36,"news-related-bb244989-00b5-4b67-b70a-5316452ee44e":55},{"id":4,"title":5,"summary":6,"content":6,"original_url":7,"source_id":8,"tags":9,"translations":23,"news_slug":29,"published_at":30,"created_at":31,"modified_at":32,"is_published":33,"publish_type":34,"image_url":13,"view_count":35},"bb244989-00b5-4b67-b70a-5316452ee44e","把 RLVR 的\"零梯度\"浪费变成有效信号：Mistral 联合剑桥用 Reasoning Arena 让推理训练提速 41%","当大模型推理训练普遍采用 RLVR 时，一个长期被忽视的问题浮出水面：同一 prompt 采样出的多条轨迹若得到相同奖励，group-relative advantage 直接归零，这些样本就被白白丢弃。Mistral AI 与剑桥大学 Han Zhou、Albert Q. Jiang 等人提出的 Reasoning Arena 框架，把这类\"零梯度\"样本重新路由到 judge 系统，通过 trace tournaments 进行两两对比，挖掘细粒度偏好信号，再用 Bradley-Terry 模型从稀疏比较图中拟合奖励估计，避免 O(n²) 的全配对开销。论文结果显示，这套机制在竞赛数学与编程基准上比标准 RLVR 平均提升 7.6%，训练加速 27%–41%，生成计算节省近 50%。基座模型是 Mistral 自家的 Ministral-3-8B-Instruct-2512，judge 用 DeepSeekMath-V2 与 Qwen3。这把\"结果导向\"的 RLVR 升级为\"过程感知\"的细粒度信号回收，是 RLVR 走向工程化效率时代的一个标志性样本。","https:\u002F\u002Farxiv.org\u002Fabs\u002F2606.09380","7437aeb9-930c-4866-a2e9-48003c1a792b",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"5e628969-6d2a-437f-998a-104e4b16cfb1","ai-progress",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"120fa59a-ff6f-4537-9bf5-f818df636a0e","benchmark",{"id":18,"name":19,"slug":19,"description":13,"color":13},"0ef8513a-0a26-42f0-b6f9-5b6dadded45c","efficiency",{"id":21,"name":22,"slug":22,"description":13,"color":13},"01598627-1ea6-4b27-a5d8-874971571a71","llm",[24],{"id":25,"lang":26,"title":27,"summary":28,"content":13},"db647df1-60b4-4a10-94aa-5217d439ed99","en","Reasoning Arena turns RLVR waste into 41% faster training","As RLVR becomes widely adopted in large-model reasoning training, a long-overlooked problem has surfaced: when multiple trajectories sampled from the same prompt receive the same reward, the group-relative advantage is directly zero, and these samples are discarded for nothing. The Reasoning Arena framework proposed by Mistral AI and Cambridge's Han Zhou, Albert Q. Jiang et al. re-routes these \"zero-gradient\" samples to a judge system, mining fine-grained preference signals through trace tournaments (pairwise comparison), then uses a Bradley-Terry model to fit reward estimates from sparse comparison graphs, avoiding the O(n²) cost of full pairwise matching. Paper results show this mechanism improves an average of 7.6% over standard RLVR on competition math and programming benchmarks, training is 27%-41% faster, and generation compute is saved by nearly 50%. The base model is Mistral's own Ministral-3-8B-Instruct-2512, with DeepSeekMath-V2 and Qwen3 as judges. This upgrade of \"outcome-oriented\" RLVR to \"process-aware\" fine-grained signal recycling is a landmark sample of RLVR moving into the engineering efficiency era.","reasoning-arena-mistral-cambridge-41pct","2026-06-08T00:00:00Z","2026-06-09T20:24:35.996291Z","2026-08-19T02:08:40.142862Z",true,"agent",292,[37,46],{"slug":38,"tag_slug":38,"title_zh":39,"title_en":40,"intro_zh":41,"intro_en":42,"id":43,"is_active":33,"created_at":44,"modified_at":45},"ai-for-science","AI for Science 2026：从 UniPert 到 GPT-Rosalind 的硬核进化","AI for Science 2026: from UniPert to GPT-Rosalind","生命科学、化学材料、物理世界模型——AI 正在从\"语言工具\"变成\"实验伙伴\"。本专题收录 AI 在三大科学方向的关键节点：UniPert 统一基因与化学扰动空间、GPT-Rosalind 端到端生命科学推理、达摩院 AI 智能体 28 小时找到 4 种超导新材料、Anthropic Claude Science 把工作台做成标准品。","From language tool to lab partner — AI is reshaping life sciences, chemistry\u002Fmaterials, and physical world models. This topic covers the key milestones: UniPert unifying genetic-chemical perturbation spaces, GPT-Rosalind's end-to-end life-sciences reasoning, DAMO's AI agent discovering 4 superconducting materials in 28 hours, and Anthropic's Claude Science workbench going mainstream.","988a4300-5fab-41c4-b5d8-63711a2dc757","2026-09-10T01:34:15.296649Z","2026-09-10T01:34:15.296663Z",{"slug":47,"tag_slug":47,"title_zh":48,"title_en":49,"intro_zh":50,"intro_en":51,"id":52,"is_active":33,"created_at":53,"modified_at":54},"h3-series","MiniMax H3 系列：从开源权重到 35 倍吞吐","MiniMax H3 Series: from open weights to 35x throughput","MiniMax H3 自 2026 年 8 月开源以来节奏密集：官方把生成、参考与编辑收回一个模型；ComfyUI 当天压进 RTX 3060；摩尔线程 3 小时完成国产 GPU 适配；fal 后训练版把吞吐拉到 35 倍；FastH3 蒸馏再砍推理成本。本专题持续追踪 H3 的发布—开源—蒸馏—部署全链路。","Since MiniMax open-sourced H3 in August 2026 the pace has been relentless: one unified omni-modal model, same-day ComfyUI support down to an RTX 3060, a 3-hour Day-0 port to Moore Threads GPUs, fal's post-trained H3 Max at 35x throughput, and FastH3 distillation cutting inference cost further. This topic tracks the full H3 chain — release, open weights, distillation, deployment.","83ef0daa-3c31-4cb3-86ed-e5ee58654d5f","2026-09-08T07:33:19.942193Z","2026-09-08T07:33:19.942209Z",{"items":56},[57,62,67,72,77,82],{"id":58,"title":59,"news_slug":60,"published_at":61},"e8168e92-d16e-452a-991c-aac74dd23ec0","预训练赢了,微调输了:Muon 的反转","muon-adamw-fine-tuning-gap-reversal","2026-11-04T01:12:00+00:00",{"id":63,"title":64,"news_slug":65,"published_at":66},"94de69e8-d5b3-4199-ac19-aa7ca4e2299f","视频RL的奖励自己调权重:EmoReward公开代码","emoreward-video-rl-self-recalibrating-rewards","2026-11-06T03:15:00+00:00",{"id":68,"title":69,"news_slug":70,"published_at":71},"37e0486a-225d-4b44-b189-206bd756210c","多轮 Agent 强化学习提升了什么:46.8% 的真相","multi-turn-agentic-rl-budget-dependence","2026-11-06T01:18:33+00:00",{"id":73,"title":74,"news_slug":75,"published_at":76},"99c1eb7b-9226-4d61-afdb-5d54f920a85c","研究品味实测:AI 智能体的想法匹配只有人类的 18%","ideataste-llm-research-taste-benchmark","2026-11-04T11:13:00+00:00",{"id":78,"title":79,"news_slug":80,"published_at":81},"a43599f1-d635-4174-9a25-6e1031c497b1","长上下文崩掉的真凶不是长度，是内容竞争","context-rot-attention-competition-not-length","2026-11-04T09:00:00+00:00",{"id":83,"title":84,"news_slug":85,"published_at":86},"65de4df2-898d-4202-8f69-ac03e203e34c","0.8B 模型算对 220 题:正确性由 Lean 证明","sketchpad-certified-arithmetic-small-vlm","2026-11-04T07:00:00+00:00"]